| { | |
| "best_metric": 0.6338666666666667, | |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0710/checkpoints/checkpoint-1332", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 1332, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 83.29154205322266, | |
| "learning_rate": 2.5606601717798212e-05, | |
| "loss": 3.8198, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.4338666666666667, | |
| "eval_loss": 3.682594060897827, | |
| "eval_runtime": 6.9724, | |
| "eval_samples_per_second": 537.836, | |
| "eval_steps_per_second": 8.462, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 539.81494140625, | |
| "learning_rate": 1.5e-05, | |
| "loss": 3.2227, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5866666666666667, | |
| "eval_loss": 2.923426866531372, | |
| "eval_runtime": 7.7635, | |
| "eval_samples_per_second": 483.027, | |
| "eval_steps_per_second": 7.6, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 203.74835205078125, | |
| "learning_rate": 4.393398282201788e-06, | |
| "loss": 2.4943, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6210666666666667, | |
| "eval_loss": 2.309011936187744, | |
| "eval_runtime": 7.0241, | |
| "eval_samples_per_second": 533.877, | |
| "eval_steps_per_second": 8.4, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 802.8485717773438, | |
| "learning_rate": 0.0, | |
| "loss": 2.1575, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6338666666666667, | |
| "eval_loss": 2.152111291885376, | |
| "eval_runtime": 6.9996, | |
| "eval_samples_per_second": 535.742, | |
| "eval_steps_per_second": 8.429, | |
| "step": 1332 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1332, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.2705716958208e+18, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |